Predication in a vector processor

CROSS-REFERENCE TO RELATED APPLICATIONS

This is a continuation application that claims the benefit of U.S. patent application Ser. No. 13/566,129 filed Aug. 3, 2012, the contents of which are incorporated by reference herein in their entirety.

BACKGROUND

The present invention relates generally to computer memory, and more particularly to predication in a vector processor.

Computer systems often require a considerable amount of high speed memory, such as random access memory (RAM), to hold information, such as data and programs, when a computer is powered and operational. Memory system demands have continued to grow as computer systems have increased performance and complexity.

Communication from a main processor to locations on memory devices can involve relatively long data access times and latency. The time it takes for the main processor to access memory can be, for example, several hundred cycles, including time to realize the data is not in cache (for memory reads), time to traverse from a processor core of the main processor to I/O, across a module or other packaging, arbitration time to establish a channel to memory in a multi-processor/shared memory system, and time to get the data into or out of a memory cell.

A vector processor may support multiple memory accesses in parallel. Supporting parallel memory accesses to multiple memory locations can increase bandwidth but also increases power consumption. The increased bandwidth may come at a cost of reduced efficiency, particularly where data accessed at one or more of the memory locations is not used in further processing.

SUMMARY

Exemplary embodiments include a system for vector processor predication in an active memory device. The system includes memory in the active memory device and a processing element in the active memory device. The processing element is configured to perform a method including decoding an instruction with a plurality of sub-instructions to execute in parallel. One or more mask bits are accessed from a vector mask register in the processing element. The one or more mask bits are applied by the processing element to predicate operation of a unit in the processing element associated with at least one of the sub-instructions.

Additional exemplary embodiments include a system for vector processor predication in an active memory device. The system includes memory in the active memory device and a processing element in the active memory device. The processing element is configured to perform a method including fetching an instruction from an instruction buffer in the processing element. The instruction, including a plurality of sub-instructions to execute in parallel, is decoded. One or more mask bits are accessed from a vector mask register in the processing element. The one or more mask bits are applied by the processing element to predicate operation of a unit in the processing element associated with at least one of the sub-instructions.

Additional features and advantages are realized through the techniques of the present invention. Other embodiments and aspects of the invention are described in detail herein and are considered a part of the claimed invention. For a better understanding of the invention with the advantages and the features, refer to the description and to the drawings.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

The subject matter which is regarded as the invention is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The forgoing and other features and advantages of the invention are apparent from the following detailed description taken in conjunction with the accompanying drawings in which:

<figref idref="DRAWINGS">FIG. 1</figref> illustrates a block diagram of a system for active memory in accordance with an embodiment;

<figref idref="DRAWINGS">FIG. 2</figref> illustrates a block diagram of a memory system with active memory in accordance with an embodiment;

<figref idref="DRAWINGS">FIG. 3</figref> illustrates a schematic diagram of a memory system with active memory in accordance with an embodiment;

<figref idref="DRAWINGS">FIG. 4</figref> illustrates a block diagram of a processing element for vector processing in an active memory device in accordance with an embodiment;

<figref idref="DRAWINGS">FIG. 5</figref> illustrates an example of a lane instruction format for vector processing in an active memory device in accordance with an embodiment;

<figref idref="DRAWINGS">FIG. 6</figref> illustrates an example of a vector mask register file in accordance with an embodiment; and

<figref idref="DRAWINGS">FIG. 7</figref> illustrates a flow diagram of a process for predication in a vector processor in accordance with an embodiment.

DETAILED DESCRIPTION

An embodiment is directed to predication in a vector processor in an active memory device. The active memory device may be any suitable memory device including a plurality of memory elements (e.g., chips) connected to a logic portion and a processing element. In an embodiment, the active memory device includes layers of memory that form a three dimensional (“3D”) memory device (e.g., a memory cube) where individual columns of chips form vaults in communication with the processing element and logic. The active memory device may include a plurality of processing elements configured to communicate to the chips and other processing elements. In an embodiment, a processing element accesses a selected address in a vault through an interconnect network. In addition, the interconnect network provides a communication path between processing elements on the active memory device as well as between processing elements and a main processor. Each vault may have an associated memory controller or logic unit that is also coupled to the interconnect network.

In embodiments, processing elements are implemented as vector processors. In a vector processor, memory accesses and arithmetic instructions can act upon full vectors or generally continuous portions of vectors, where vectors enable parallel processing on multiple data elements. For some operations, memory accesses or calculations for randomly distributed elements of the vectors may be immaterial. To reduce traffic through a memory hierarchy, and the associated energy consumed, by unnecessary memory accesses, the vector processors include vector mask register files for use in predication of instructions and as targets of comparison instructions. Predication of instructions allows for selective execution of certain elements of the vectors based on a mask. The vector processors also provide support for vector mask generation, logical operations on vector masks, and automatic reduction of vector mask registers to summary condition bits. The vector mask bits can be automatically reduced to a single condition bit as a summary of generated mask bits during comparisons, for use during future conditional branch instructions. Instructions within the vector processor architecture are capable of being predicated. Memory access instructions, in particular, are useful, when predicated, for reducing unnecessary traffic through the memory hierarchy, and for conserving energy during such situations. Use of predication during arithmetic operations can also eliminate the need for permuting of data, by providing for “on-the-fly” construction of a vector which contains only desired, piece-meal components from various operations.

Embodiments include an active memory device that can perform a complex set of operations using multiple locations (e.g., data stored at specific addresses) within the active memory device as operands. Further, a process is provided whereby the instructions and operations are performed autonomously on these operands within the active memory device. Specifically, the instructions are stored within the active memory device itself and are not executed by a main processor. The stored instructions are provided to the processing elements for processing by the processing element in the active memory device. In one embodiment, the processing elements are programmable engines, including an instruction buffer, an instruction unit with branching capability and instruction decode, a mixture of vector, scalar, and mask register files, a plurality of load/store units for the movement of data between memory and the register files, and a plurality of execution units for the arithmetic and logical processing of various data types. Also included in the active memory device are address translation capabilities for converting virtual addresses to physical addresses, a unified Load/Store Queue to sequence data movement between the memory and the processing elements, and a processor communications unit, for communication with the main processor.

In an embodiment, the active memory device is configured to load configuration information or instructions from a part of the active memory device into a processing element following receiving a command from an external requestor, such as a main processor or another processing element. In addition, the processing element may perform virtual-to-real address translations that are computed while executing the loaded instructions. In an example, when performing a load instruction, the active memory device accesses an operand from a memory location and places the operand in a register in the processing element. A virtual address of the memory location is generated by the load instruction and is translated into a real address by the processing element. Similarly, when performing a store instruction, the active memory device writes a memory location with the contents (e.g., an operand) in a register in the processing element. A virtual address of the memory location is generated by the store instruction and is translated into a real address by the processing element.

Embodiments of the processing element in the active memory device also have the ability to read or to write operands in any part of the active memory device through the interconnect network. Specifically, a processing element may access other vaults in the active memory device using the interconnect network. In an embodiment, processing elements are pooled and coupled to the vaults via the interconnect network, where the processing elements are not physically located in the vault stack. In an embodiment, the interconnect network is a coupling device, such as a crossbar switch, configured to connect any processing element to any memory vault, provided the processing element and memory vault are coupled to the interconnect. In an embodiment, the interconnect network may couple a plurality of active memory devices, where the interconnect network provides a communication path between processing elements and memory vaults of separate devices.

In one embodiment, the processing element is included with the memory controller as part of the stack. In addition, the processing element may perform complex arithmetic and logic operations on the operands, and read and write end results back to locations in memory. The active memory device may return a single result value or signal to the main processor indicating that the results of the desired complex operation are ready in the active memory device, thus performing the high bandwidth processing on the active memory device and using a lower bandwidth communication between the active memory device and main processor.

The processing capabilities within an active memory device may reduce memory latency and energy consumption that would otherwise be experienced when memory is accessed by a processor residing in a separate chip. Instead of bringing data from memory to the separate processing chip through lower bandwidth communication paths, performing what is often quite simple calculations on the data, and then transferring the processed data back to memory, the main processor can configure the processing elements within the active memory device, and then instruct them to carry out the data processing tasks. This may be achieved by sending one or more commands from the main processor to the active memory device. In this scenario, the movement of data between the location where the data processing is performed and memory is greatly reduced, both in the distance it has to travel from the memory to the data processing location, and in the number of levels of cache traversed through a memory hierarchy.

<figref idref="DRAWINGS">FIG. 1</figref> illustrates a block diagram of a system for storing and retrieving data in a memory in accordance with an embodiment. A system <b>100</b> depicted in <figref idref="DRAWINGS">FIG. 1</figref> includes a computer processor (CPU) <b>102</b>, a memory <b>106</b> having memory devices, as well as a memory controller <b>104</b> and processing element <b>108</b> for receiving and processing data from the computer processor <b>102</b> to be stored in the memory <b>106</b>.

The memory controller <b>104</b> may be in communication with the computer processor <b>102</b> and receive write requests from the computer processor <b>102</b> without using functions of the processing element <b>108</b>. The write requests contain data to be written to the memory <b>106</b> and a real address for identifying the location in the memory <b>106</b> to which the data will be written. The memory controller <b>104</b> stores data at a real address within the memory <b>106</b>. The computer processor <b>102</b> can map the virtual address to a real address in the memory <b>106</b> when storing or retrieving data. The real address for a given virtual address may change each time data in the memory <b>106</b> is modified.

In an embodiment, the processing element <b>108</b> is in communication with the computer processor <b>102</b> and receives a command from the computer processor <b>102</b>. The command may correspond to instructions stored in the memory <b>106</b> to perform write requests for data to be written to the memory <b>106</b>. The command may also include a virtual address for identifying the location in the memory <b>106</b> to which the data will be written. The memory controller <b>104</b> and/or processing element <b>108</b> stores data at a real address within the memory <b>106</b>. In an embodiment, the processing element <b>108</b> maps the virtual address to a real address in the memory <b>106</b> when storing or retrieving data. As described in further detail below, the computer processor <b>102</b> provides commands to the memory <b>106</b>, where the processing element <b>108</b> receives the command and fetches corresponding instructions from the memory <b>106</b>. The system <b>100</b> is one example of a configuration that may be utilized to perform the processing described herein. Although the system <b>100</b> has been depicted with only a single memory <b>106</b>, memory controller <b>104</b>, processing element <b>108</b> and computer processor <b>102</b>, it will be understood that other embodiments would also operate in other systems with two or more of the memory <b>106</b>, memory controller <b>104</b>, processing element <b>108</b> or computer processor <b>102</b>. In an embodiment, the memory <b>106</b>, memory controller <b>104</b>, processing element <b>108</b> and computer processor <b>102</b> are not located within the same computer. For example, the memory <b>106</b>, processing element <b>108</b> and memory controller <b>104</b> may be located in one physical location (e.g., on a memory module) while the computer processor <b>102</b> is located in another physical location (e.g., the computer processor <b>102</b> accesses the memory controller <b>104</b> and/or processing element <b>108</b> via a network). In addition, portions of the processing described herein may span one or more of the memory <b>106</b>, memory controller <b>104</b>, processing element <b>108</b> and computer processor <b>102</b>.

<figref idref="DRAWINGS">FIG. 2</figref> is a schematic diagram of an embodiment of a computer system <b>200</b> implementing active memory. In one embodiment, the computer system <b>200</b> includes an active memory device <b>202</b>, an active memory device <b>203</b> and an active memory device <b>204</b>. The active memory device <b>202</b> includes a memory vault <b>206</b>, a memory controller <b>208</b> and a processing element <b>210</b>. In an embodiment, the processing element <b>210</b>, memory vault <b>206</b> and memory controller <b>208</b> are coupled and communicate via an interconnect network <b>212</b>. Specifically, the processing element <b>210</b> communicates to the memory vault <b>206</b>, memory controller <b>208</b> and other memory devices, such as active memory devices <b>203</b> and <b>204</b>, via the interconnect network <b>212</b>. The interconnect network <b>212</b> is also coupled to a main processor <b>224</b> by processor links <b>220</b> and <b>222</b>. The interconnect network <b>212</b> provides a fast and high bandwidth path for communication between portions of the device, such processing elements, memory controllers and memory, to provide improved performance and reduced latency for the active memory.

The active memory device <b>203</b> includes a memory vault <b>226</b>, a memory controller <b>228</b> and a processing element <b>230</b>. In an embodiment, the processing element <b>230</b>, memory vault <b>226</b> and memory controller <b>228</b> are all located on the same side of the interconnect network <b>212</b>, such as within a single stack. By positioning the processing element <b>230</b> in the same stack as memory vault <b>226</b>, the latency is reduced when accessing locations in the memory vault <b>226</b>, thus further improving performance. In one embodiment, the active memory <b>204</b> includes a memory vault <b>214</b> and memory controller <b>216</b> coupled to processing element <b>210</b> and processing element <b>218</b> via the interconnect network <b>212</b>. As depicted, the processing element <b>218</b> is located on the other side of the interconnect network <b>212</b> from the memory controller <b>216</b> and memory vault <b>214</b>. In embodiments, the active memory devices <b>202</b>, <b>203</b> and <b>204</b> include multiple layers of stacked addressable memory elements. Further, the stacks memory may be divided into memory vaults <b>206</b>, <b>226</b> and <b>214</b>, or three-dimensional blocked regions of the memory device which share a common memory controller and/or memory element, and are capable of servicing memory access requests to their domain of memory independently of one another.

In embodiments, the processing elements, memory vaults and memory controllers may be arranged in a suitable manner depending on the application. For example, one or more processing elements, such as processing element <b>218</b>, may be positioned on one side of the interconnect network <b>212</b> and may operate as a pool of processing elements that are available for accessing any memory in the memory system coupled to the interconnect network <b>212</b>. The pooled processing elements are not limited to accessing a particular memory vault and, thus, one or more elements may be utilized upon receiving a command from the main processor <b>224</b>. Accordingly, processing element <b>218</b> may be configured to access each memory vault <b>206</b>, <b>226</b> and <b>214</b>. In another embodiment, one or more processing element, such as processing element <b>230</b>, is located as part of a stack including a memory vault <b>226</b> and memory controller <b>228</b>. In such a configuration, the processing element <b>230</b> is configured to access memory vault <b>226</b> coupled to the interconnect network <b>212</b>, including memory vaults <b>206</b> and <b>214</b>. In one embodiment, one or more processing element, such as processing element <b>210</b>, is positioned on an opposite side of the interconnect network <b>212</b> from the memory vault <b>206</b> and memory controller <b>208</b>. In the configuration, the processing element <b>210</b> is configured to access any memory coupled to the interconnect network <b>212</b>, including memory vaults <b>226</b> and <b>214</b>.

In an embodiment, the computer system may include a plurality of active memory devices, such as the active memory devices <b>202</b>, <b>203</b> and <b>204</b>. Further, each active memory device may include a plurality of stacks, each stack including a memory vault, memory controller and associated processing element. In one example, the number of processing elements may be greater than the number of memory vaults. In another embodiment, the memory devices may include fewer processing elements than memory vaults. In embodiments, the processing elements are pooled and available to access any memory in the system. For example, a memory device may include 16 memory vaults and memory controllers, but only eight processing elements. The eight processing elements are pooled, and utilized as resources for accessing any memory vaults coupled to the interconnect network. In another example, a memory device may be passive, where the device is controlled by processing elements of active memory devices coupled to the interconnect network.

<figref idref="DRAWINGS">FIG. 3</figref> is a diagram of an exemplary computer system <b>300</b> implementing active memory. The computer system <b>300</b> includes a circuit board <b>302</b>, a main processor <b>304</b>, active memory device <b>306</b> and active memory device <b>308</b>. The active memory device <b>306</b>, active memory device <b>308</b> and main processor <b>304</b> are disposed on the circuit board <b>302</b>. As depicted, portions of the active memory devices <b>306</b> and <b>308</b> are exploded to show details of the computer system <b>300</b> arrangement. The active memory devices <b>306</b> and <b>308</b> communicate to the main processor <b>304</b> via signal paths <b>324</b> and <b>344</b>, respectively. As depicted, the active memory <b>306</b> device is arranged in layers, where a base layer <b>311</b> includes a plurality of memory controllers <b>310</b> and processing elements <b>312</b>. For example, the active memory device <b>306</b> includes layers <b>309</b> of memory placed on top of the base layer <b>311</b>, where the layers <b>309</b> each have a plurality of memory elements. As depicted, the base layer <b>311</b> also includes an interconnect network <b>346</b> to enable high bandwidth communication between memory, memory controllers and processing elements in the device.

In an embodiment, the active memory device <b>306</b> includes a plurality of memory vaults <b>314</b>, where each memory vault <b>314</b> includes a memory element from each layer <b>309</b>, the memory vaults <b>314</b> positioned adjacent to memory controllers <b>310</b> and processing elements <b>312</b>. Specifically, the exemplary active memory device <b>306</b> includes layers of 16 memory elements, where the element layers form stacks, including a stack <b>316</b>, where the stack <b>316</b> includes a memory vault <b>322</b> disposed above a memory controller <b>318</b> and a processing element <b>320</b>. A high bandwidth communication path <b>326</b> provides a high bandwidth, direct and substantially reduced length (e.g., as compared to paths <b>324</b>, <b>344</b>) communication path between the processing element <b>320</b> and memory locations within the memory vault <b>322</b>, thus reducing latency and power consumption for memory accesses. For example, the processing element <b>320</b> may receive a command from the main processor <b>304</b>, load instructions from within the active memory device <b>306</b> based on the command, and, as part of the loaded instructions, access data at a location in the memory vault <b>314</b> and perform a complex operation on the data in the processing element <b>320</b>. Further, the processing element <b>320</b> may also store data, such as the result, in the memory vault <b>314</b> and transmit a value or signal to the main processor <b>304</b> following execution of the command. In an embodiment, the processing element <b>320</b> stores or writes data (e.g. an operand) from a register in the processing element <b>320</b> to the memory vault <b>314</b>. The processing element <b>320</b> is also configured to translate addresses from virtual-to-real and real-to-virtual as part of the read or store operations. Thus, the processing element <b>320</b> provides instruction loading, address translation, complex operations and other tasks local to the memory to reduce latency, save power and free up the main processor <b>304</b> to perform other tasks.

Similarly, the active memory device <b>308</b> includes a plurality of memory controllers <b>328</b> and processing elements <b>330</b> disposed on a base layer <b>331</b>. In an embodiment, the active memory <b>308</b> includes layers <b>329</b> of memory devices placed on top of the base layer <b>331</b>, where the layers <b>329</b> each have a plurality of memory devices. The base layer <b>331</b> also includes an interconnect network <b>346</b> to enable high bandwidth communication between memory and processing elements in the device. In an embodiment, the interconnect networks <b>346</b> of active memory device <b>306</b> and active memory device <b>308</b> are coupled and allow communication between processing elements and memory on separate devices.

In an embodiment, the active memory device <b>308</b> includes a plurality of memory vaults <b>332</b>, where each memory vault <b>332</b> includes a memory element from each layer <b>329</b>, the memory vaults <b>332</b> are positioned adjacent to memory controllers <b>328</b> and processing elements <b>330</b>. The exemplary active memory device <b>308</b> includes 16 stacks, including stack <b>334</b>, where the stack <b>334</b> includes a memory vault <b>336</b> disposed above a memory controller <b>340</b> and a processing element <b>338</b>. A high bandwidth communication path <b>342</b> provides communication between the processing element <b>330</b> and memory locations within the memory vault <b>336</b>.

<figref idref="DRAWINGS">FIG. 4</figref> depicts an example of a processing element <b>400</b> coupled to an interconnect network <b>402</b> as an embodiment of one of the processing elements of <figref idref="DRAWINGS">FIGS. 1-3</figref>. The processing element <b>400</b> is a vector processor, situated in an active memory device, such as one of the active memory devices of <figref idref="DRAWINGS">FIGS. 1-3</figref>. In the example of <figref idref="DRAWINGS">FIG. 4</figref>, the processing element <b>400</b> includes a load-store queue (LSQ) <b>404</b> coupled to the interconnect network <b>402</b> and to an instruction buffer <b>406</b>. The instruction buffer <b>406</b> is also coupled to a lane control unit (LCU) <b>408</b> and a decoder <b>410</b>. A processor communication unit (PCU) <b>412</b> provides a communication interface between the processing element <b>400</b> and the main processor or other processing elements through the interconnect network <b>402</b>. The LSQ <b>404</b> is also coupled to a vector computation register file (VCR) <b>414</b>, a scalar computation register file (SCR) <b>416</b>, and a vector mask register file (VMR) <b>424</b>. The VCR <b>414</b> and SCR <b>416</b> are coupled through multiple multiplexers to an arithmetic logic unit (ALU) <b>418</b> and a memory-access unit <b>420</b>, also referred to as a load-store unit (LSU) <b>420</b>. The ALU <b>418</b> is coupled to itself and to the LSU <b>420</b> through multiplexers, and is also coupled to the VCR <b>414</b> and the SCR <b>416</b>. The LSU <b>420</b> may also be coupled to itself, to the LSQ <b>404</b>, to an effective-to-real address translation unit (ERAT) <b>422</b>, to the VCR <b>414</b> and to the SCR <b>416</b> (all connections not depicted). The ERAT <b>422</b> is also coupled to the LSQ <b>404</b>. The VMR <b>424</b> is coupled to the LSQ <b>404</b>, an output of the ALU <b>418</b>, and to inputs of the ALU <b>418</b> and LSU <b>420</b> through multiplexers. As will be appreciated, numerous other connections and elements can be included in the processing element <b>400</b>. For example, connections between the decoder <b>410</b> and other elements are not depicted for clarity. Additionally, depicted connections in <figref idref="DRAWINGS">FIG. 4</figref> can be modified or omitted, such as the depicted connection between decoder <b>410</b> and PCU <b>412</b>.

The processing element <b>400</b> supports an instruction set architecture including a broad range of arithmetic capabilities on many data types. Vector processing capabilities of the processing element <b>400</b> allows for single instruction, multiple data (SIMD) in time, while SIMD in a spatial dimension is also supported. The instruction buffer <b>406</b> holds instructions (also referred to as “lane instructions”), which are fetched and executed in order subject to branching. In an embodiment, each lane instruction contains 9 sub-instructions for execution in various units within the processing element <b>400</b>. An iteration count may be included within the lane instruction, allowing the sub-instructions to be repeated up to a predetermined number of times (e.g., up to 32 times). This facilitates SIMD in time. The LCU <b>408</b> can manage the iteration count and determine when to advance to a next instruction or repeat execution of the same instruction. In an embodiment, arithmetic pipelines of ALU <b>418</b> are 64 bits wide, and spatial SIMD is supported by virtue of the ability to execute data types smaller than 64 bits in parallel, simultaneously as multiple execution slots. For example, assuming that a lane instruction includes 9 sub-instructions, execution of the sub-instructions can be performed in the LCU <b>408</b> for lane control, and in four processing slices, each of which includes an ALU <b>418</b> and an LSU <b>420</b>. Pairs of the VCR <b>414</b> and the SCR <b>416</b> can be implemented per processing slice and are accessible by each pair of the ALU <b>418</b> and LSU <b>420</b>. Each processing slice may also include a VMR <b>424</b> and a condition register (CR) <b>426</b>. Accordingly, the VCR <b>414</b>, SCR <b>416</b>, ALU <b>418</b>, LSU <b>420</b>, VMR <b>424</b>, CR <b>426</b> and associated multiplexers are depicted as stacks of four elements to indicate 4 processing slices in the example of <figref idref="DRAWINGS">FIG. 4</figref>.

At the processing slice level, computation can occur on floating-point and fixed-point data types at, for example, a 64-bit granularity in a temporal SIMD manner on 64-bit vector elements, and in a temporal and spatial SIMD manner on narrower vector sub-elements, which can be 32-bits, 16-bits, or 8-bits wide.

Each processing slice within the processing element <b>400</b> includes a memory access pipeline (load/store pipeline) and an arithmetic pipeline. Managing flow through the LSU <b>420</b> as a load/store pipeline can enable computation of one address per vector data element or sub-element. The processing element <b>400</b> provides the ability to perform associated fixed-point effective address (i.e., virtual address) computations. The arithmetic pipeline through the ALU <b>418</b> can include a robust assortment of floating-point and fixed-point operations to support a variety of workloads.

The LSU <b>420</b> may support load and store operations of, for example, 8, 4, 2 and 1 byte(s) and load and store operations of 4, 2, and 1 byte(s) to and from registers with packed data.

The ALU <b>418</b> may support copy operations between register files, arithmetic, rounding and conversion, comparison, and maximum and minimum operations on floating-point data types of double-precision (64 bits) and single-precision (32 bits), and arithmetic, rotate/shift, comparison, logical, count leading zeros, and ones population count operations on fixed-point data types of doubleword (64 bits), word (32 bits), halfword (16 bits) and bytes (8 bits).

In an embodiment, the computational model of a processing slice within the processing element <b>400</b> is a vector single instruction multiple data (SIMD) model with the VCR <b>414</b> and SCR <b>416</b>. The VCR <b>414</b> can support multiple dimensions of registers, while the SCR <b>416</b> supports a single dimension of registers. For example, the VCR <b>414</b> can include 16 register entries with 32 elements each of 64 bits, and the SCR <b>416</b> can include 16 register entries with 1 element each of 64 bits, although numerous other configurations may be supported. The VMR <b>424</b> also has multiple dimensions of registers. For example, the VMR <b>424</b> can include 4 register entries with 32 elements each of 8 bits. SIMD instructions access multiple data in different cycles, and for data types smaller than one register element, also access multiple data in space in each cycle. When a SIMD instruction accesses a register entry of the VCR <b>414</b> or VMR <b>424</b>, one element of each accessed entry is accessed per cycle. If a register entry of the VMR <b>424</b> is used as a predicate, one element of the register entry is associated with each cycle of the SIMD instruction's execution. A variable number of execution slots can be used, operating on an equal number of sub-elements, whereby the sub-elements taken together add up to one register element (either VCR <b>414</b> or SCR <b>416</b>) of 64 bits in this example. The number of execution slots and the corresponding number of vector sub-elements depend upon the data type of the instruction. Examples of data types and sizes of various formats include: floating-point with double-precision (64-bit) and single-precision (32-bit) data types and fixed-point for a doubleword (64-bit), word (32-bit), halfword (16-bit), and byte (8-bit) data types.

The VMR <b>424</b> can be used to enable different functional behavior on different vector elements without conditional branches. For example, mask bits in the VMR <b>424</b> can be used in the LSU <b>420</b> to prevent issuing non-functional load/store requests and avoid unnecessary power consumption in the memory system. Mask bits of the VMR <b>424</b> can also be used to reduce and throttle power within processing pipelines of the processing element <b>400</b>. For example, the mask bits of the VMR <b>424</b> can be used as early inputs to clock-gating logic for pipeline stages and register files, avoiding unnecessary clock and data power in the pipelines and register files of the ALU <b>418</b>, LSU <b>420</b>, VCR <b>414</b> and SCR <b>416</b>. SIMD-in-space instructions have multiple vector sub-elements in each pipeline cycle and multiple mask bits per cycle. Control logic for these instructions can use the mask bits of the VMR <b>424</b> to clock- or data-gate different parts (e.g., different bytes) of the datapath and enable partial writes to the register files.

In exemplary embodiments, the processing element <b>400</b> includes ALU <b>418</b> and LSU <b>420</b> instructions that write to entries of the VMR <b>424</b>. The processing element <b>400</b> may also include an instruction to load VMR <b>424</b> data from memory. The processing element <b>400</b> can include a compare instruction which writes results of each element comparison of a multi-element comparison to the VMR <b>424</b>. The number of bits per VMR <b>424</b> element is the maximum number of SIMD-in-space comparisons which can occur per cycle. When a compare instruction using the maximum SIMD-in-space parallelism executes, there is a one-to-one correspondence between comparison results and VMR bits. When a compare instruction using less than the maximum SIMD-in-space parallelism executes, there is a one-to-N correspondence between comparison results and VMR bits, with N&gt;1. A compare instruction writes a summary of all sub-element compares to the CR <b>426</b>. The compare instruction syntax can include a bit that determines whether the summary is an OR-reduction or an AND-reduction. When a compare instruction is predicated, the mask operand controls which sub-element comparisons contribute to the summary.

The processing element <b>400</b> can also include a compare instruction with syntax that includes a bit to determine whether the current value of the CR <b>426</b> is included in the reduction to produce the new value in the CR <b>426</b>, or not. The processing element <b>400</b> may include an instruction that computes a mask result as a logical function of one or more mask operands for the VMR <b>424</b>. The processing element may include an instruction to move data from the VCR <b>414</b> or the SCR <b>416</b> to the VMR <b>424</b>. The processing element <b>400</b> can also include an instruction that computes a mask result as a function of one or more numeric operands (e.g., put is only in the first N elements).

In an exemplary embodiment, the processing element <b>400</b> includes an LSU <b>420</b> instruction that stores VMR <b>424</b> data to memory. The processing element <b>400</b> can also include an ALU <b>418</b> instruction that moves data from the VMR <b>424</b> to the VCR <b>414</b> or the SCR <b>416</b>. The processing element <b>400</b> may include an ALU <b>418</b> instruction with a VMR <b>424</b> operand that computes a numeric result (e.g., population count). During the execution of a predicated ALU <b>418</b> instruction that computes one element per cycle (not SIMD-in-space), when the mask bit for one element is 0, the corresponding element of the target vector register is not changed.

During the execution of a predicated ALU <b>418</b> instruction that computes more than one sub-element per cycle (SIMD-in-space), when the mask bit for one sub-element is 0, that sub-element of the result may be boundedly undefined.

An example of a lane instruction format <b>500</b> is depicted in <figref idref="DRAWINGS">FIG. 5</figref> as a processing element operation which utilizes and controls all of the resources within processing element <b>400</b> of <figref idref="DRAWINGS">FIG. 4</figref>. In the example of <figref idref="DRAWINGS">FIG. 5</figref>, the lane instruction format <b>500</b> includes a 5-bit iteration count (IC) field <b>502</b>, a 1-bit iteration count select (ICS) field <b>504</b>, and nine sub-instructions. The sub-instructions include a 19-bit branch (BU) sub-instruction <b>506</b>, which executes once and controls the sequence of lane instruction execution, four 31-bit memory access or load-store (LSU) sub-instructions <b>508</b>, <b>512</b>, <b>516</b>, <b>520</b> (one per processing slice 0-3), which execute one or more times per lane instruction, and four 41-bit arithmetic-logical (ALU) sub-instructions <b>510</b>, <b>514</b>, <b>518</b>, <b>522</b> (one per processing slice 0-3), which execute one or more times per lane instruction. The IC field <b>502</b> within a lane instruction, or an iteration count register, as selected by the ICS field <b>504</b>, determines the number of times that the ALU and LSU sub-instructions are repeated. The BU sub-instruction <b>506</b> may be referred to generally as a lane control (LCU) sub-instruction for the LCU <b>408</b> and can include other control operations, such as returning, pausing, and no-operation, in addition to branching.

Each sub-instruction is a processor operation which utilizes and controls all of the resources within a given unit within the processing element <b>400</b>. If a sub-instruction contains all scalar registers in the SCR <b>416</b> for the target and source(s), then the sub-instruction can be executed during execution of a first element of the lane instruction. Lane control sub-instructions, including branch sub-instructions, can be executed during execution of the last element of the lane instruction. Conditions for branch sub-instructions may be evaluated during execution of the first element of the lane instruction.

<figref idref="DRAWINGS">FIG. 6</figref> illustrates an example of VMR <b>424</b> of <figref idref="DRAWINGS">FIG. 4</figref> in accordance with an embodiment. In the example of <figref idref="DRAWINGS">FIG. 6</figref>, VMR <b>424</b> includes 128 registers <b>602</b> arranged as 4 entries of 32 elements each. Each group of 4 registers <b>602</b> represents 4 entries that are routed to an entry selection multiplexer <b>604</b> per element per output port. Output ports A, B, C, and S provide outputs to support a number of operations using vector mask bits of the registers <b>602</b>. Element selection multiplexers <b>606</b> allow for a selected entry and selected element combination to be routed to each of the output ports A, B, C, and S, where the final output for each port can be used for particular processing operations per processing slice. For example, output ports A and B can be used for mask logic operations, output port C can be used for mask bits for predicated instructions, and output port S can be used to mask data for stores.

<figref idref="DRAWINGS">FIG. 7</figref> depicts an example process <b>700</b> for predication in a vector processor in an active memory device, such as the active memory devices of <figref idref="DRAWINGS">FIGS. 1-3</figref>. The blocks depicted in <figref idref="DRAWINGS">FIG. 7</figref> may be performed by one of the processing elements of <figref idref="DRAWINGS">FIGS. 1-4</figref> in an active memory device. For example, the blocks may be performed by a processing element in an active memory device, where the processing element accesses portions of memory (e.g., memory vaults sharing a stack with the processing element) and performs operations on data accessed from the memory. For purposes of explanation, the processing element is described in reference to processing element <b>400</b> of <figref idref="DRAWINGS">FIG. 4</figref>.

At block <b>702</b>, processing element <b>400</b> decodes an instruction including a plurality of sub-instructions to execute in parallel. The instruction can be fetched from instruction buffer <b>406</b> and decoded by decoder <b>410</b>. The instruction may be in a lane instruction format <b>500</b> to support parallel execution of ALU and LSU instructions. At block <b>704</b>, one or more mask bits are accessed from VMR <b>424</b> in the processing element <b>400</b>. At block <b>706</b>, the one or more mask bits are applied by the processing element <b>400</b> to predicate operation of a unit in the processing element <b>400</b> associated with at least one of the sub-instructions. The one or more mask bits can be an instruction mask to block execution of one or more elements of the sub-instructions or execution of one or more execution slots operating on a sub-element of a sub-instruction. Mask bits of the VMR <b>424</b> can be used block a memory access sub-instruction of the LSU <b>420</b> or block part of an arithmetic operation of the ALU <b>418</b>. The mask bits of the VMR <b>424</b> can also be used to perform clock or data gating at the VCR <b>414</b>, SCR <b>416</b>, ALU <b>418</b>, and/or LSU <b>420</b>.

At block <b>708</b>, loading, logical operations, or compares can be used to populate and modify mask bit values in the VMR <b>424</b>. For example, the mask bit values of the VMR <b>424</b> can be populated from one or more of the memory and the ALU <b>418</b>. The processing element <b>400</b> can perform logical operations on the mask bit values to modify the mask bit values of the VMR <b>424</b>. The VMR <b>424</b> can also be used for comparisons. For example, when the processing element <b>400</b> performs a compare of operands, using, for example the ALU <b>418</b>, compare results may be stored as mask bit values to the VMR <b>424</b>. The VMR <b>424</b> can include a plurality of vector mask entries, each including a plurality of elements of mask bits, forming two-dimensional vector masks in the VMR <b>424</b>. Multiple mask bits may be generated per cycle per element based on single instruction, multiple data-in-space compare operations to form the two-dimensional vector masks in the VMR <b>424</b>. The two-dimensional vector masks can be used with two-dimensional vector data, where the two-dimensional vector masks correspond to data sub-elements in the two-dimensional vector data to predicate.

At block <b>710</b>, the mask bit values can be reduced to a summary condition, and the summary condition written to CR <b>426</b>. The processing element <b>400</b> can determine whether the summary condition is an OR-reduction or an AND-reduction based on compare instruction syntax. Based on determining that the summary condition is the OR-reduction, the CR <b>426</b> is written as a logical OR combination of the compare results. Based on determining that the summary condition is the AND-reduction, the CR <b>426</b> is written as a logical AND combination of the compare results. The summary condition in the CR <b>426</b> can span multiple instructions. For example, the OR-reduction or the AND-reduction can also include a past value (or present value before update) of the CR <b>426</b> as part of the summary condition determination. At block <b>712</b>, the summary condition in the CR <b>426</b> can be used as a condition for determining a branch direction (e.g., take/don't take) of a conditional branch instruction in the processing element <b>400</b>.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one more other features, integers, steps, operations, element components, and/or groups thereof.

The corresponding structures, materials, acts, and equivalents of all means or step plus function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed. The description of the present invention has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the invention. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated

The flow diagrams depicted herein are just one example. There may be many variations to this diagram or the steps (or operations) described therein without departing from the spirit of the invention. For instance, the steps may be performed in a differing order or steps may be added, deleted or modified. All of these variations are considered a part of the claimed invention.

While the preferred embodiment to the invention had been described, it will be understood that those skilled in the art, both now and in the future, may make various improvements and enhancements which fall within the scope of the claims which follow. These claims should be construed to maintain the proper protection for the invention first described.